diff options
author | Jaegeuk Kim <jaegeuk@kernel.org> | 2014-06-13 06:07:31 +0200 |
---|---|---|
committer | Jaegeuk Kim <jaegeuk@kernel.org> | 2014-06-23 03:05:08 +0200 |
commit | 98397ff3cddcfdedd2ba1701bd30a73c1d733769 (patch) | |
tree | 2f3180fcfe2057df1c849482cebd7d1b6fe1c179 /fs | |
parent | f2fs: recover fallocated data and its i_size together (diff) | |
download | linux-98397ff3cddcfdedd2ba1701bd30a73c1d733769.tar.xz linux-98397ff3cddcfdedd2ba1701bd30a73c1d733769.zip |
f2fs: fix not to allocate unnecessary blocks during fallocate
This patch fixes the fallocate bug like below. (See xfstests/255)
In fallocate(fd, 0, 20480),
expand_inode_data processes
for (index = pg_start; index <= pg_end; index++) {
f2fs_reserve_block();
...
}
So, even though fallocate requests 20480, 5 blocks, f2fs allocates 6 blocks
including pg_end.
So, this patch adds one condition to avoid block allocation.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Diffstat (limited to 'fs')
-rw-r--r-- | fs/f2fs/file.c | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index f6c4bdaaae86..7d8b96275092 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -664,11 +664,14 @@ static int expand_inode_data(struct inode *inode, loff_t offset, for (index = pg_start; index <= pg_end; index++) { struct dnode_of_data dn; + if (index == pg_end && !off_end) + goto noalloc; + set_new_dnode(&dn, inode, NULL, NULL, 0); ret = f2fs_reserve_block(&dn, index); if (ret) break; - +noalloc: if (pg_start == pg_end) new_size = offset + len; else if (index == pg_start && off_start) |